kevinveenbirkenbach/skills
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

docs(skills): fetch CI artifacts before theorising

Browse Source 
A job log usually names an artifact path and stops there; the assertion
text, server exception and state dumps live inside the artifact. Both
triage and dialectic now require downloading them before forming a
thesis, since theorising from the log alone while an unread artifact
holds the answer is the most expensive mistake in the loop.

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
This commit is contained in:
Kevin Veen-Birkenbach
2026-07-31 11:55:42 +02:00
parent 04f24bb16d
commit 545c213f88
2 changed files with 18 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files

7
skills/dialectic/SKILL.md
View File

@@ -26,6 +26,13 @@ operator holds.
git history; the running containers (exec, logs, inspect through whatever git history; the running containers (exec, logs, inspect through whatever
make or CLI helpers the project exposes); CI logs and artifacts; tests; docs. make or CLI helpers the project exposes); CI logs and artifacts; tests; docs.
Cite `file:line` and command output — never a bare assertion. Cite `file:line` and command output — never a bare assertion.
**Download the artifacts before theorising.** When the failure comes from a
CI run, list its artifacts and fetch every one that could carry the failure
(`gh run download <run> -n <name> -D <dir>`, or the equivalent for the CI in
use). A job log routinely holds only the *path* of a report while the payload
— assertion text, expected vs received, server logs, diagnostic dumps — lives
in the artifact. Theorising from the log alone while an unread artifact
contains the answer is the single most expensive mistake in this loop.
2. **Antithesis.** Spawn MULTIPLE independent skeptics (parallel subagents or a 2. **Antithesis.** Spawn MULTIPLE independent skeptics (parallel subagents or a
workflow) whose only job is to REFUTE the thesis. Each re-inspects the workflow) whose only job is to REFUTE the thesis. Each re-inspects the
sources itself and defaults to "refuted" on any concrete hole. Give diverse sources itself and defaults to "refuted" on any concrete hole. Give diverse

15
skills/triage/SKILL.md
View File

@@ -17,20 +17,27 @@ root cause is proven.
whose conclusion is failure, cancelled, or timed-out. A downstream aggregate whose conclusion is failure, cancelled, or timed-out. A downstream aggregate
job that fails only because an upstream job did is not a separate root cause — job that fails only because an upstream job did is not a separate root cause —
note it and move on. note it and move on.
2. **Dialectic per failing job.** For EACH failing job, invoke the `dialectic` 2. **Download the run's artifacts.** Before investigating, list the run's
artifacts and fetch every one belonging to a failing job — reports, rescue
diagnostics, inventories, container logs. The job log usually names an
artifact path and nothing more; the assertion text, the server-side
exception and the state dumps are inside the artifact. Do this even when the
log looks conclusive, because a log that explains the symptom rarely
explains the cause.
3. **Dialectic per failing job.** For EACH failing job, invoke the `dialectic`
skill: form a thesis about the root cause from evidence (the job log, its skill: form a thesis about the root cause from evidence (the job log, its
artifacts, the code at the run's commit, git history), attack it with artifacts, the code at the run's commit, git history), attack it with
independent skeptics, and iterate to a ~99% thesis. The jobs are independent, independent skeptics, and iterate to a ~99% thesis. The jobs are independent,
so run their investigations in parallel where the tooling allows. so run their investigations in parallel where the tooling allows.
3. **Distinguish shared vs hidden causes.** When several jobs share one root 4. **Distinguish shared vs hidden causes.** When several jobs share one root
cause, fix it once. When a job hides a second failure behind the first, keep cause, fix it once. When a job hides a second failure behind the first, keep
going until the job is actually green, not just past the first error. going until the job is actually green, not just past the first error.
4. **Fix at the root.** Apply the real fix in the repository for each proven root 5. **Fix at the root.** Apply the real fix in the repository for each proven root
cause. Never mask a failure — no retry-until-pass, no disabling the check, no cause. Never mask a failure — no retry-until-pass, no disabling the check, no
soft-skip. If a failure is genuinely external (upstream outage, flaky infra), soft-skip. If a failure is genuinely external (upstream outage, flaky infra),
confirm that with evidence and surface it honestly instead of fixing around confirm that with evidence and surface it honestly instead of fixing around
it. it.
5. **Follow the run.** While the run is still in progress, re-check it 6. **Follow the run.** While the run is still in progress, re-check it
periodically and triage each newly failed job as it appears. The run is done periodically and triage each newly failed job as it appears. The run is done
only when it has finished and every failure has a verified fix. only when it has finished and every failure has a verified fix.